Chronic intracranial recordings in the globus pallidus reveal circadian rhythms in Parkinson's disease.

Circadian rhythms have been shown in the subthalamic nucleus (STN) in Parkinson's disease (PD), but only a few studies have focused on the globus pallidus internus (GPi). This retrospective study investigates GPi circadian rhythms in a large cohort of subjects with PD (130 recordings from 93 subjects) with GPi activity chronically recorded in their home environment. We found a significant change in GPi activity between daytime and nighttime in most subjects (82.4%), with a reduction in GPi activity at nighttime in 56.2% of recordings and an increase in activity in 26.2%. GPi activity in higher frequency bands ( > 20 Hz) was more likely to decrease at night and in patients taking extended-release levodopa medication. Our results suggest that circadian fluctuations in the GPi vary across individuals and that increased power at night might be due to the reemergence of pathological neural activity. These findings should be considered to ensure successful implementation of adaptive neurostimulation paradigms in the real-world.

Mitigating gut microbial degradation of levodopa and enhancing brain dopamine: Implications in Parkinson's disease.

Parkinson's disease is managed using levodopa; however, as Parkinson's disease progresses, patients require increased doses of levodopa, which can cause undesirable side effects. Additionally, the oral bioavailability of levodopa decreases in Parkinson's disease patients due to the increased metabolism of levodopa to dopamine by gut bacteria, Enterococcus faecalis, resulting in decreased neuronal uptake and dopamine formation. Parkinson's disease patients have varying levels of these bacteria. Thus, decreasing bacterial metabolism is a promising therapeutic approach to enhance the bioavailability of levodopa in the brain. In this work, we show that Mito-ortho-HNK, formed by modification of a naturally occurring molecule, honokiol, conjugated to a triphenylphosphonium moiety, mitigates the metabolism of levodopa-alone or combined with carbidopa-to dopamine. Mito-ortho-HNK suppresses the growth of E. faecalis, decreases dopamine levels in the gut, and increases dopamine levels in the brain. Mitigating the gut bacterial metabolism of levodopa as shown here could enhance its efficacy.

Impaired sequence manipulation in non-demented patients with progressive supranuclear palsy.

PURPOSE: Sequential working memory is the ability to maintain and manipulate sequential information at a second time scale. Patients with progressive supranuclear palsy (PSP) or Parkinson's disease (PD) perform poorly in tests that require the flexible arrangement of thoughts or actions. This study investigated whether sequential working memory is differently impaired in patients with PSP versus PD. METHOD: Twenty-nine patients with PSP Richardson's syndrome (PSP-RS), 36 patients with PD, and 36 healthy controls (HC) completed 3 well-established neuropsychological tests, including digit span forward (DST-F), digit span backward (DST-B), and adaptive digit ordering tests (DOT-A). The DST-F required maintaining digit sequences, and the DST-B and DOT-A required maintaining and manipulating digit sequences. FINDING: The PSP-RS group scored lower than the PD and HC groups in the DST-B and DOT-A but not in the DST-F, indicating that the ability to manipulate sequences was impaired, but the maintenance ability was preserved in PSP-RS patients. Moreover, in PSP-RS, the DST-B score negatively correlated with the severity of motor symptoms. The actual levodopa dose positively correlated with the DST-B ordering cost (DST-F score vs. DST-B score). The PSP patients who took a greater dose of levodopa tended to have higher DST-B ordering cost. There was no effect of levodopa on DST-B or DOT-A in PD. CONCLUSION: These results suggested that the ability to manipulate sequence was already reduced in patients with PSP-RS and was worse than in patients with PD.

Effect of Direct and Mediated through Maternal Organism Activation of the Catecholaminergic System on Heart Rate Parameters in Rat Fetuses.

We performed a comparative analysis of direct and mediated through the maternal organism effects of elevated catecholamine concentration on changes in the cardiac activity parameters in female rats and their fetuses on gestation days 18 and 20 under in vivo conditions. Administration of L-DOPA, a precursor of catecholaminergic transmitters, did not cause chronotropic effects in fetuses. Analysis of HR variability showed that in fetuses, irrespective of the administration route, there was an increase in nervous influences while the leading role of humoral-metabolic factors in the regulation of HR was preserved. In females receiving L-DOPA injection on day 18 of gestation, a decrease in humoral-metabolic and an increase in nerve effects were observed; in rats injected with L-DOPA on day 20 of gestation, an increase in sympathetic influences was found. Administration of L-DOPA to fetuses provoked a slight increase in the power of all components of the heart rhythm periodogram spectrum in females on day 18 of gestation and their decrease on day 20. Changes in the parameters of HR variability in females can confirm the hypothesis that in the "mother-fetus" system, the heart rhythm in the mother can be affected by both maternal and fetal influences presumably through the humoral-metabolic regulation.

Harnessing Graphdiyne for Selective Cu2+ Detection: A Promising Tool for Parkinson's Disease Diagnostics and Pathogenesis.

Cu2+ accelerates the viral-like propagation of α-synuclein fibrils and plays a key role in the pathogenesis of Parkinson's disease (PD). Therefore, the accurate detection of Cu2+ is essential for the diagnosis of PD and other neurological diseases. The Cu2+ detection process is impeded by substances that have similar electrochemical properties. In this study, graphdiyne (GDY), a new kind of carbon allotrope with strong electron-donating ability, was utilized for the highly selective detection of Cu2+ by taking advantage of its outstanding adsorption capacity for Cu2+. Density functional theory (DFT) calculations show that Cu atoms are adsorbed in the cavity of GDY, and the absorption energy between Cu and C atoms is higher than that of graphene (GR), indicating that the cavity of GDY is favorable for the adsorption of Cu atoms and electrochemical sensing. The GDY-based electrochemical sensor can effectively avoid the interference of amino acids, metal ions and neurotransmitters and has a high sensitivity of 9.77 µA·µM-1·cm-2, with a minimum detectable concentration of 200 nM. During the investigating pathogenesis and therapeutic process of PD with α-synuclein as the diagnostic standard, the concentration of Cu2+ in cells before and after L-DOPA and GSH treatments were examined, and it was found that Cu2+ exhibits high potential as a biomarker for PD. This study not only harnesses the favorable adsorption of the GDY and Cu2+ to improve the specificity of ion detection but also provide clues for deeper understanding of the role of Cu2+ in neurobiology and neurological diseases.

Pyruvate dehydrogenase-E1α deficiency presenting as generalized dystonia: A genetic diagnosis with important clinical implications.

Pyruvate dehydrogenase complex (PDC) deficiency is a genetic mitochondrial disease mostly associated with severe lactic acidosis, rapid progression of neurological symptoms and death during childhood. We present a 33-year-old male with PDC deficiency caused by a Val262Leu mutation in PDHA1gene. He demonstrated generalized dystonia affecting trunk and upper extremities and paraparesis as the most significant features, with onset of symptoms at age 8. Brain MRI showed bilaterally increased signal within the globus pallidus, typical of Leigh syndrome. A periodic lactate increase in serum and cerebrospinal fluid was detected. We describe a case of pyruvate dehydrogenase deficiency being diagnosed only 25 years after the onset of symptoms and highlight PDHC deficiency as a possible cause of treatable dystonia in childhood, which may respond well to thiamine and levodopa treatment.

Parkinson's Kinetigraph for Wearable Sensor Detection of Clinically Unrecognized Early-Morning Akinesia in Parkinson's Disease: A Case Report-Based Observation.

Early-morning off periods, causing early-morning akinesia, can lead to significant motor and nonmotor morbidity in levodopa-treated fluctuating Parkinson's disease (PD) cases. Despite validated bedside scales in clinical practice, such early-morning off periods may remain undetected unless specific wearable technologies, such as the Parkinson's KinetiGraph™ (PKG) watch, are used. We report five PD cases for whom the PKG detected early-morning off periods that were initially clinically undetected and as such, untreated. These five cases serve as exemplars of this clinical gap in care. Post-PKG assessment, clinicians were alerted and targeted therapies helped abolish the early-morning off periods.

Kinetic Properties and Pharmacological Modulation of High- and Low-Affinity Dopamine Transport in Striatal Astrocytes of Adult Rats.

Astrocytes actively participate in neurotransmitter homeostasis by bidirectional communication with neuronal cells, a concept named the tripartite synapse, yet their role in dopamine (DA) homeostasis remains understudied. In the present study, we investigated the kinetic and molecular mechanisms of DA transport in cultured striatal astrocytes of adult rats. Kinetic uptake experiments were performed using radiolabeled [3H]-DA, whereas mRNA expression of the dopamine, norepinephrine, organic cation and plasma membrane monoamine transporters (DAT, NET, OCTs and PMAT) and DA receptors D1 and D2 was determined by qPCR. Additionally, astrocyte cultures were subjected to a 24 h treatment with the DA receptor agonist apomorphine, the DA receptor antagonist haloperidol and the DA precursor L-DOPA. [3H]-DA uptake exhibited temperature, concentration and sodium dependence, with potent inhibition by desipramine, nortriptyline and decynium-22, suggesting the involvement of multiple transporters. qPCR revealed prominent mRNA expression of the NET, the PMAT and OCT1, alongside lower levels of mRNA for OCT2, OCT3 and the DAT. Notably, apomorphine significantly altered NET, PMAT and D1 mRNA expression, while haloperidol and L-DOPA had a modest impact. Our findings demonstrate that striatal astrocytes aid in DA clearance by multiple transporters, which are influenced by dopaminergic drugs. Our study enhances the understanding of regional DA uptake, paving the way for targeted therapeutic interventions in dopaminergic disorders.

Dopamine and its precursor levodopa inactivate SARS-CoV-2 main protease by forming a quinoprotein.

Many studies show either the absence, or very low levels of, SARS-CoV-2 viral RNA and/or antigen in the brain of COVID-19 patients. Reports consistently indicate an abortive infection phenomenon in nervous cells despite the fact that they contain the SARS-CoV-2 receptor, ACE2. Dopamine levels in different brain regions are in the range of micromolar to millimolar concentrations. We have shown that sub-micromolar to low micromolar concentrations of dopamine or its precursor (levodopa) time- and dose-dependently inhibit the activity of SARS-CoV-2 main protease (Mpro), which is vital for the viral life cycle, by forming a quinoprotein. Thiol detection coupled with the assessment of Mpro activity suggests that among the 12 cysteinyl thiols, the active site, Cys145-SH, is preferentially conjugated to the quinone derived from the oxidation of dopamine or levodopa. LC-MS/MS analyses show that the Cys145-SH is covalently conjugated by dopamine- or levodopa-o-quinone. These findings help explain why SARS-CoV-2 causes inefficient replication in many nerve cell lines. It is well recognized that inhaled pulmonary drug delivery is the most robust therapy pathway for lung diseases. CVT-301 (orally inhaled levodopa) was approved by the FDA as a drug for Parkinson's patients prior to the outbreak of COVID-19 in 2018. Based on the fact that SARS-CoV-2 causes inefficient replication in the CNS with abundant endogenous Mpro inhibitor in addition to the current finding that levodopa has an Mpro-inhibitory effect somewhat stronger than dopamine, we should urgently investigate the use of CVT-301 as a lung-targeting, COVID-19, Mpro inhibitor.

The effects of L-DOPA on gait abnormalities in a unilateral 6-OHDA rat model of Parkinson's disease.

Parkinson's Disease (PD) is a neurodegenerative movement disorder characterized by dopamine (DA) cell loss in the substantia nigra pars compacta (SNc). As PD progresses, patients display disruptions in gait such as changes in posture, bradykinesia, and shortened stride. DA replacement via L-DOPA alleviates many PD symptoms, though its effects on gait are not well demonstrated. This study aimed to assess the relationship between DA lesion, gait, and deficit-induced reversal with L-DOPA. To do so, Sprague-Dawley rats (N = 25, 14 males, 11 females) received unilateral medial forebrain bundle (MFB) DA lesions with 6-hydroxydopamine (6-OHDA). An automated gait analysis system assessed spatiotemporal gait parameters pre- and post-lesion, and after various doses of L-DOPA (0, 3, or 6 mg/kg; s.c.). The forepaw adjusting steps (FAS) test was implemented to evaluate lesion efficacy while the abnormal involuntary movements (AIMs) scale monitored the emergence of L-DOPA-induced dyskinesia (LID). High performance liquid chromatography (HPLC) assessed changes in brain monoamines on account of lesion and treatment. Results revealed lesion-induced impairments in gait, inclusive of max-contact area and step-sequence alterations that were not reversible with L-DOPA. However, the emergence of AIMs were observed at higher doses. Post-mortem, 6-OHDA lesions induced a loss of striatal DA and norepinephrine (NE), while prefrontal cortex (PFC) displayed noticeable reduction in NE but not DA. Our findings indicate that hemiparkinsonian rats display measurable gait disturbances similar to PD patients that are not rescued by DA replacement. Furthermore, non-DA mechanisms such as attention-related NE in PFC may contribute to altered gait and may constitute a novel target for its treatment.

The Gut Microbiota in Parkinson Disease: Interactions with Drugs and Potential for Therapeutic Applications.

The concept of a 'microbiota-gut-brain axis' has recently emerged as an important player in the pathophysiology of Parkinson disease (PD), not least because of the reciprocal interaction between gut bacteria and medications. The gut microbiota can influence levodopa kinetics, and conversely, drugs administered for PD can influence gut microbiota composition. Through a two-step enzymatic pathway, gut microbes can decarboxylate levodopa to dopamine in the small intestine and then dehydroxylate it to m-tyramine, thus reducing availability. Inhibition of bacterial decarboxylation pathways could therefore represent a strategy to increase levodopa absorption. Other bacterial perturbations common in PD, such as small intestinal bacterial overgrowth and Helicobacter pylori infection, can also modulate levodopa metabolism, and eradication therapies may improve levodopa absorption. Interventions targeting the gut microbiota offer a novel opportunity to manage disabling motor complications and dopa-unresponsive symptoms. Mediterranean diet-induced changes in gut microbiota composition might improve a range of non-motor symptoms. Prebiotics can increase levels of short-chain fatty acid-producing bacteria and decrease pro-inflammatory species, with positive effects on clinical symptoms and levodopa kinetics. Different formulations of probiotics showed beneficial outcomes on constipation, with some of them improving dopamine levels; however, the most effective dosage and duration and long-term effects of these treatments remain unknown. Data from faecal microbiota transplantation studies are preliminary, but show encouraging trends towards improvement in both motor and non-motor outcomes.This article summarises the most up-to-date knowledge in pharmacomicrobiomics in PD, and discusses how the manipulation of gut microbiota represents a potential new therapeutic avenue for PD.

Concomitant treatment with safinamide and antidepressant drugs: Safety data from real clinical practice.

BACKGROUND AND PURPOSE: The aim of this study was to assess the possible pharmacological interactions between safinamide and antidepressants, and in particular the appearance of serotonin syndrome with data from real life. METHODS: We conducted a retrospective observational study of patients with Parkinson's disease from our Movement Disorders Unit, who were under treatment with any antidepressant drug and safinamide. Specifically, symptoms suggestive of serotonin syndrome were screened for. Also, we collected time of simultaneous use, doses of levodopa and other antiparkinsonian drugs. RESULTS: Clinical records were reviewed for the study period of September 2018 to September 2019. Seventy-eight PD patients who were treated with safinamide of which 25 (32.05%) had a concomitant treatment with an antidepressant drug, being sertraline and escitalopram the most frequent. Mean age was 80 years±8.43 and H&Y stage was 3 [2-4]. Mean dose of levodopa used was 703.75mg±233.15. Median duration of concomitant treatment with safinamide and antidepressant drug was 6 months (IQR 20.5), and over eighteen months in 5 cases. No case of serotonin syndrome was recorded, neither was any of its typical manifestations combined or in isolation. CONCLUSIONS: Our real clinical practice study suggests that concomitant use of safinamide with antidepressant drugs in PD patients seemed to be safe and well tolerated, even in the long term. However, caution is warranted, individualizing treatment regimens and monitoring the potential appearance of adverse effects.

Delayed levodopa-responsive parkinsonism following acute midbrain injury.

Acute midbrain injury may cause both hyperkinetic movement disorders and parkinsonism. The temporal interval between the insult and the emergence of hyperkinetic disorders can last years. A delayed appearance of parkinsonism, on the other hand, was rarely described. We present three cases of male patients (50-, 58- and 28-year-old) who developed levodopa-responsive parkinsonism 20, 8 and two years, respectively, after acute brain insult involving the midbrain. Insults included subcortical intracerebral hemorrhage dissecting into the midbrain, embolic basilar occlusion and trauma. A fluorodopa scan, performed in two cases, revealed reduced striatal uptake. All individuals improved on low doses of levodopa and developed motor fluctuations shortly after levodopa was introduced. We conclude that delayed, levodopa-responsive parkinsonism following midbrain injury should be recognized in the relevant clinical setup. Possible mechanisms include age-related loss of dopaminergic neurons superimposed on acute injury and secondary neurodegeneration.

A randomized feasibility trial of medium chain triglyceride-supplemented ketogenic diet in people with Parkinson's disease.

BACKGROUND: A ketogenic diet (KD) may benefit people with neurodegenerative disorders marked by mitochondrial depolarization/insufficiency, including Parkinson's disease (PD). OBJECTIVE: Evaluate whether a KD supplemented by medium chain triglyceride (MCT-KD) oil is feasible and acceptable for PD patients. Furthermore, we explored the effects of MCT-KD on blood ketone levels, metabolic parameters, levodopa absorption, mobility, nonmotor symptoms, simple motor and cognitive tests, autonomic function, and resting-state electroencephalography (rsEEG). METHODS: A one-week in-hospital, double-blind, randomized, placebo-controlled diet (MCT-KD vs. standard diet (SD)), followed by an at-home two-week open-label extension. The primary outcome was KD feasibility and acceptability. The secondary outcome was the change in Timed Up & Go (TUG) on day 7 of the diet intervention. Additional exploratory outcomes included the N-Back task, Unified Parkinson's Disease Rating Scale, Non-Motor Symptom Scale, and rsEEG connectivity. RESULTS: A total of 15/16 subjects completed the study. The mean acceptability was 2.3/3, indicating willingness to continue the KD. Day 7 TUG time was not significantly different between the SD and KD groups. The nonmotor symptom severity score was reduced at the week 3 visit and to a greater extent in the KD group. UPDRS, 3-back, and rsEEG measures were not significantly different between groups. Blood ketosis was attained by day 4 in the KD group and to a greater extent at week 3 than in the SD group. The plasma levodopa metabolites DOPAC and dopamine both showed nonsignificant increasing trends over 3 days in the KD vs. SD groups. CONCLUSIONS: An MCT-supplemented KD is feasible and acceptable to PD patients but requires further study to understand its effects on symptoms and disease. TRIAL REGISTRATION: Trial Registration Number NCT04584346, registration dates were Oct 14, 2020 - Sept 13, 2022.

Genetically encoded biocompatible anti-coagulant protein-coated coronary artery stents drive endothelialization.

In response to the critical demand for advancements in coronary artery stents, this study addresses the challenges associated with arterial recoil and restenosis post-angioplasty and the imperative to encourage rapid re-endothelialization for minimizing thrombosis risks. We employed an innovative approach inspired by mussel adhesion, incorporating placental anticoagulant protein (AnnexinV) on stent design. The introduction of a post-translationally modified catecholic amino acid L-3,4-dihydroxyphenylalanine (L-Dopa), mimicking mussel characteristics, allowed for effective surface modification of Stainless steel stents through genetic code engineering in AnnexinV (AnxDopa). The efficacy of AnxDopa was analyzed through microscale thermophoresis and flow cytometry, confirming AnxDopa's exceptional binding with phosphatidylserine and activated platelets. AnxDopa coated stainless steel demonstrates remarkable bio-, hemo-, and immuno-compatibility, preventing smooth muscle cell proliferation, platelet adhesion, and fibrin formation. It acts as an interface between the stent and biological fluid, which facilitates the anticoagulation and rapid endothelialization. Surface modification of SS verified through XPS analysis and contact angle measurement attests to the efficacy of AnxDopa mediated surface modification. The hydrophilic nature of the AnxDopa-coated surface enhanced the endothelialization through increased protein absorption. This approach represents a significant stride in developing coronary stents with improved biocompatibility and reduced restenosis risks, offering valuable contributions to scientific and clinical realms alike.

L-DOPA regulates neuroinflammation and Aß pathology through NEP and ADAM17 in a mouse model of AD.

Dopamine plays important roles in cognitive function and inflammation and therefore is involved in the pathogenesis of neurodegenerative diseases, including Alzheimer's disease (AD). Drugs that increase or maintain dopamine levels in the brain could be a therapeutic strategy for AD. However, the effects of dopamine and its precursor levodopa (L-DOPA) on Aß/tau pathology in vivo and the underlying molecular mechanisms have not been studied in detail. Here, we investigated whether L-DOPA treatment alters neuroinflammation, Aß pathology, and tau phosphorylation in 5xFAD mice, a model of AD. We found that L-DOPA administration significantly reduced microgliosis and astrogliosis in 5xFAD mice. In addition, L-DOPA treatment significantly decreased Aß plaque number by upregulating NEP and ADAM17 levels in 5xFAD mice. However, L-DOPA-treated 5xFAD mice did not exhibit changes in tau hyperphosphorylation or tau kinase levels. These data suggest that L-DOPA alleviates neuroinflammatory responses and Aß pathology but not tau pathology in this mouse model of AD.

Quaternary Ammonium Assisted Synthesis of Melanin-like Poly(l-DOPA) Nanoparticles with a Boosted Photothermal Effect.

Poly(levodopa) nanoparticles (P(l-DOPA) NPs) are another kind of melanin mimetic besides well-established polydopamine nanoparticles (PDA NPs). Due to the presence of carboxyl groups, the oxidative polymerization of l-DOPA to obtain particles was not as efficient as that of dopamine. Several established methods toward P(l-DOPA) NP fabrication do not combine convenience, morphological regularity, size controllability, low cost, and adaptability to metal-free application scenarios. In this work, P(l-DOPA) NPs were successfully prepared in hot water with the assistant of organic quaternary ammonium, due to the extra physical cross-linking mediated by cations. The employed physical interactions could also be affected by quaternary ammonium structure (i.e., number of cation heads, length of alkyl chain) to achieve different polymerization acceleration effects. The obtained P(l-DOPA) NPs retained superior photothermal properties and outperformed PDA-based melanin materials. Furthermore, P(l-DOPA) NPs were used in photothermal tumor therapy and showed better efficacy. This study offers new insights into the synthesis of melanin-like materials, as well as new understanding of the interaction between quaternary ammonium and bioinspired polyphenolic materials.

Metabolite profiling of foslevodopa/foscarbidopa in plasma of healthy human participants by LC-HRMS indicates no major differences compared to administration of levodopa/carbidopa intestinal gel.

Analysis was conducted to compare levodopa/carbidopa pharmacokinetics and drug-related material in plasma of healthy participants after receiving a continuous infusion of Levodopa/Carbidopa Intestinal Gel (LCIG) to a continuous subcutaneous infusion of foslevodopa/foscarbidopa. Study samples were from a randomized, open-label, 2-period crossover study in 20 healthy participants. Participants received either 24-h foslevodopa/foscarbidopa SC infusion to the abdomen or LCIG delivered for 24 h to the jejunum through a nasogastric tube with jejunal extension. Serial blood samples were collected for PK. Comparability of the LD PK parameters between the two treatment regimens was determined. Selected plasma samples were pooled per treatment group and per time point for metabolite profiling. LC-MSn was performed using high-resolution mass spectrometry to identify drug-related material across the dosing regimens and time points. The LD PK parameter central values and 90% confidence intervals following the foslevodopa/foscarbidopa subcutaneous infusion were between 0.8 and 1.25 relative to the LCIG infusion. With LCIG administration, LD, CD, 3-OMD, DHPA, DOPAC, and vanillacetic acid were identified in plasma at early and late time points (0.75 and 24 h); the metabolic profile after administration of foslevodopa/foscarbidopa demonstrated the same drug-related compounds with the exception of the administered foslevodopa. 3-OMD and vanillacetic acid levels increased over time in both treatment regimens. Relative quantification of LC-MS peak areas showed no major differences in the metabolite profiles. These results indicate that neither the addition of monophosphate prodrug moieties nor SC administration affects the circulating metabolite profile of foslevodopa/foscarbidopa compared to LCIG.

A decision support system based on recurrent neural networks to predict medication dosage for patients with Parkinson's disease.

Using deep learning has demonstrated significant potential in making informed decisions based on clinical evidence. In this study, we deal with optimizing medication and quantitatively present the role of deep learning in predicting the medication dosage for patients with Parkinson's disease (PD). The proposed method is based on recurrent neural networks (RNNs) and tries to predict the dosage of five critical medication types for PD, including levodopa, dopamine agonists, monoamine oxidase-B inhibitors, catechol-O-methyltransferase inhibitors, and amantadine. Recurrent neural networks have memory blocks that retain crucial information from previous patient visits. This feature is helpful for patients with PD, as the neurologist can refer to the patient's previous state and the prescribed medication to make informed decisions. We employed data from the Parkinson's Progression Markers Initiative. The dataset included information on the Unified Parkinson's Disease Rating Scale, Activities of Daily Living, Hoehn and Yahr scale, demographic details, and medication use logs for each patient. We evaluated several models, such as multi-layer perceptron (MLP), Simple-RNN, long short-term memory (LSTM), and gated recurrent units (GRU). Our analysis found that recurrent neural networks (LSTM and GRU) performed the best. More specifically, when using LSTM, we were able to predict levodopa and dopamine agonist dosage with a mean squared error of 0.009 and 0.003, mean absolute error of 0.062 and 0.030, root mean square error of 0.099 and 0.053, and R-squared of 0.514 and 0.711, respectively.